import os
import pickle
from contextlib import nullcontext
import torch
import tiktoken
from model import GPTConfig, GPT
import random

out_dir = 'out-cricket-commentary' # ignored if init_from is not 'resume'
start = "\n" # or "<|endoftext|>" or etc. Can also specify a file, use as: "FILE:prompt.txt"
num_samples = 1 #10 # number of samples to draw
max_new_tokens = 300 #500 # number of tokens generated in each sample
temperature = 0.8 # 1.0 = no change, < 1.0 = less random, > 1.0 = more random, in predictions
top_k = 50 #200 # retain only the top_k most likely tokens, clamp others to have 0 probability
seed = random.randint(1, 10000)
device = 'cuda' if torch.cuda.is_available() else 'cpu' # examples: 'cpu', 'cuda', 'cuda:0', 'cuda:1', etc.
dtype = 'bfloat16' if torch.cuda.is_available() and torch.cuda.is_bf16_supported() else 'float16' # 'float32' or 'bfloat16' or 'float16'
compile = False # use PyTorch 2.0 to compile the model to be faster
#exec(open('configurator.py').read()) # overrides from command line or config file
# -----------------------------------------------------------------------------

torch.manual_seed(seed)
torch.cuda.manual_seed(seed)
torch.backends.cuda.matmul.allow_tf32 = True # allow tf32 on matmul
torch.backends.cudnn.allow_tf32 = True # allow tf32 on cudnn
device_type = 'cuda' if 'cuda' in device else 'cpu' # for later use in torch.autocast
ptdtype = {'float32': torch.float32, 'bfloat16': torch.bfloat16, 'float16': torch.float16}[dtype]
ctx = nullcontext() if device_type == 'cpu' else torch.amp.autocast(device_type=device_type, dtype=ptdtype)

ckpt_path = os.path.join(out_dir, 'ckpt.pt')

enc = tiktoken.get_encoding("gpt2")
encode = lambda s: enc.encode(s, allowed_special={"<|endoftext|>"})
decode = lambda l: enc.decode(l)